Most of volumetric 3D reconstruction methods need accurate silhouette information of foreground objects for the reliable 3D scene reconstruction of the objects. We present an approach to silhouette extraction based on our change detection method [1] using a statistical model and graph cuts based optimization. We describe some requirements for visual hull reconstruction. We show that our change detection method is appropriate to satisfy these requirements. We analyze our methodology through experiments and have shown the feasibility of reliable extraction of silhouettes. Consequently, we can reconstruct the 3D shape more accurately than by other change detection methods.